© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87550
    Prev
    Next
    INDEX
    Explanations

    detailed references to academic programs and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evi
    -0.07
    esian
    -0.07
    /frontend
    -0.07
    zon
    -0.06
    pesan
    -0.06
    Å¡ek
    -0.06
     neighboring
    -0.06
     UNUSED
    -0.06
     Olson
    -0.06
    :\/\/
    -0.06
    POSITIVE LOGITS
     Edition
    0.16
     edition
    0.13
    Edition
    0.12
    edition
    0.10
    ç¯ĩ
    0.09
    çīĪ
    0.09
     version
    0.09
     Branch
    0.08
     branch
    0.08
     Version
    0.07
    Activations Density 0.092%

    No Known Activations